Fig. 1: Estimated effects of the CWCRT programme on confirmatory outcomes.
From: Emergency mental health co-responders reduce involuntary psychiatric detentions in the USA
The analytic sample consists of a balanced panel of 48 neighbourhoods over 54 months (N = 2,592). The reported estimates are based on conditional maximum likelihood Poisson specifications that include neighbourhood and month–year fixed effects. All tests of statistical significance are two-tailed. Bootstrapped standard errors are blocked at the neighbourhood level. Dots are point estimates; bars are 95% CIs. See Supplementary Table 3 for fully reported results.
